Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3040 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.8965. Min Range: -5.8965

Max Act: 5.8965. Min Act: -0.0000

Data Index: 270127 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 5.8965. Min Range: -5.8965

Max Act: 5.5529. Min Act: -0.0000

Data Index: 728778 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 5.8965. Min Range: -5.8965

Max Act: 5.6107. Min Act: -0.0000

Data Index: 967954 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 5.8965. Min Range: -5.8965

Max Act: 5.2876. Min Act: -0.0000

Data Index: 1078393 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 5.8965. Min Range: -5.8965

Max Act: 5.1257. Min Act: -0.0000

Data Index: 254617 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 5.8965. Min Range: -5.8965

Max Act: 5.2878. Min Act: -0.0000

Data Index: 1087906 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.9794. Min Act: -0.0000

Data Index: 67239 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.8633. Min Act: -0.0000

Data Index: 876685 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.9976. Min Act: -0.0000

Data Index: 757777 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.9265. Min Act: -0.0000

Data Index: 1029773 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.5233. Min Act: -0.0000

Data Index: 1119927 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.5642. Min Act: -0.0000

Data Index: 628257 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.4900. Min Act: -0.0000

Data Index: 555118 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.4659. Min Act: -0.0000

Data Index: 1162847 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.4920. Min Act: -0.0000

Data Index: 386713 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.4535. Min Act: -0.0000

Data Index: 162754 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.6224. Min Act: -0.0000

Data Index: 1209333 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.8281. Min Act: -0.0000

Data Index: 540309 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.1146. Min Act: -0.0000

Data Index: 25424 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 5.8965. Min Range: -5.8965

Max Act: 4.0933. Min Act: -0.0000

Data Index: 587712 (C4 (Web Text))

Max Activating Token Index: 906